SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags
party
Programmatic guide for the @cazala/party library: engine setup, modules, particle APIs, and performance tips for WebGPU and CPU runtimes.
swarm-ai-safety
Research framework for simulating multi-agent systems to assess emergent risks, governance levers, and soft probabilistic metrics (toxicity, quality gap).
party
Guidance and examples for using the @cazala/party particle engine (engine lifecycle, modules, WebGPU vs CPU patterns) in custom apps.
crush-skill
Create a private, local AI profile of a romantic interest from chat logs, photos, and social media using parsers and Bayesian tagging — for personal analysis an
claude-skill-registry
Two-step Solana swap workflow: quote/simulate first, present clear summary, then execute only after explicit user confirmation to avoid accidental trades.
crush-skills
Create and evolve a personalised crush conversational Skill from chat logs, photos, and social media; generates Relationship Memory and Persona for simulation a
agent-lsp
Simulate code edits in-memory using an LSP-backed session to verify diagnostics and prevent breaking changes before writing to disk.
insurance-skills
Guides AI agents to build PolicyPulse: a Python-based synthetic population simulator with clean architecture, type-safe code patterns, and Streamlit dashboard d
tb2j
Expert guidance for using TB2J command-line tools to extract magnetic interaction parameters (J, DMI, anisotropy) from DFT outputs and prepare inputs/outputs fo
botstreet
Run a research-driven virtual portfolio manager: update prices, research, make trades, write a diary entry, and save daily snapshots for a simulated $100k accou
gateflow-plugin
Orchestrates SystemVerilog/RTL development: plan, generate, verify, and iterate using specialist agents to deliver working, lint-clean, tested RTL.
afsim-script-generator
Generate, validate, and execute AFSIM 2.9.0 scenario scripts; helps produce syntactically correct .txt mission scripts, run them with mission.exe, and debug com
agent-almanac
Build and analyze discrete or continuous Markov chains: transition matrices, state classification, stationary distributions, and mean first-passage times.
mean-reviewer-skill
Generates an aggressive, exhaustive simulated peer review for stress-testing manuscripts and rebuttal workflows; includes mandatory license/acceptance gating.
insurance-skills
Guidance for building PolicyPulse — a synthetic-population simulation dashboard with clean architecture, strong Python typing, and Streamlit UI patterns.
